Delete app.py

app.py

@@ -1,105 +0,0 @@
-import gradio as gr
-import joblib
-import pandas as pd
-from fastapi import FastAPI, Request
-from fastapi.responses import JSONResponse
-import uvicorn
-from sklearn.linear_model import LinearRegression
-from sklearn.model_selection import train_test_split
-
-# Hardcoded mappings
-phase_map = { "Framing": 0, "Foundation": 1, "Finishing": 2}
-weather_map = {"Cloudy": 0, "Rainy": 1, "Sunny": 2}
-
-# Load and preprocess training data
-df = pd.read_csv("delay_data.csv")
-
-# Encode categorical features
-df["Phase"] = df["Phase"].map(phase_map)
-df["Weather"] = df["Weather"].map(weather_map)
-
-# Handle missing or invalid mappings
-df.dropna(subset=["Phase", "Weather", "Absentee", "DelayLog", "Delay%"], inplace=True)
-
-# Split features and target
-X = df[["Phase", "Weather", "Absentee", "DelayLog"]]
-y = df["Delay%"]
-
-# Train model
-model = LinearRegression()
-model.fit(X, y)
-
-# Main prediction function
-def predict_delay(phase, weather, absentee_pct, delay_log):
-    phase_encoded = phase_map.get(phase, 0)
-    weather_encoded = weather_map.get(weather, 0)
-    input_data = [[phase_encoded, weather_encoded, absentee_pct, delay_log]]
-    
-    # Model makes prediction
-    prediction = model.predict(input_data)[0]
-    prediction = round(prediction, 2)
-
-    # Risk tagging based on predicted delay percentage
-    if prediction >= 75:
-        risk = "High Risk"
-    elif prediction >= 50:
-        risk = "Moderate Risk"
-    else:
-        risk = "Low Risk"
-
-    # AI reasoning for insights
-    insight = f"Phase: {phase}, Weather: {weather}, Absenteeism: {absentee_pct}%, Previous Delay: {delay_log} → Risk: {risk}"
-
-    return prediction, risk, insight
-
-# FastAPI for Salesforce
-api_app = FastAPI()
-
-@api_app.post("/predict")
-async def predict_from_salesforce(request: Request):
-    try:
-        data = await request.json()
-        phase = data.get("phase", "Framing")
-        weather = data.get("weather", "Sunny")
-        absentee_pct = float(data.get("absentee_pct", 0))
-        delay_log = float(data.get("delay_log", 0))
-
-        prediction, risk, insight = predict_delay(phase, weather, absentee_pct, delay_log)
-
-        return JSONResponse(content={
-            "delay_probability": prediction,
-            "risk_alert": risk,
-            "ai_insight": insight,
-            "status": "success"
-        })
-    except Exception as e:
-        return JSONResponse(status_code=500, content={"status": "error", "message": str(e)})
-
-# Gradio UI for manual testing
-with gr.Blocks() as demo:
-    gr.Markdown("## 🏗️ Delay Predictor")
-    with gr.Row():
-        phase_input = gr.Textbox(label="Phase (Framing/Foundation/Finishing)")
-        weather_input = gr.Textbox(label="Weather (Sunny/Rainy/Cloudy)")
-    with gr.Row():
-        absentee_input = gr.Number(label="Absentee %")
-        delay_input = gr.Number(label="Previous Delay Log")
-    output = gr.Textbox(label="Prediction Summary")
-
-    def predict_and_format(phase, weather, absentee, delay_log):
-        prediction, risk, insight = predict_delay(phase, weather, absentee, delay_log)
-        return f"Predicted Delay: {prediction}%\nRisk Level: {risk}\nInsight: {insight}"
-
-    submit = gr.Button("Predict")
-    submit.click(
-        predict_and_format,
-        inputs=[phase_input, weather_input, absentee_input, delay_input],
-        outputs=output
-    )
-
-# Mount Gradio inside FastAPI
-app = gr.mount_gradio_app(api_app, demo, path="/")
-
-# Run locally (Hugging Face will ignore this)
-if __name__ == "__main__":
-    uvicorn.run(app, host="0.0.0.0", port=7860)